VGG识别眼疾iChallenge-PM

内容都是百度AIstudio的内容，我只是在这里做个笔记，不是原创。

VGG是当前最流行的CNN模型之一，2014年由Simonyan和Zisserman提出，其命名来源于论文作者所在的实验室Visual Geometry Group。AlexNet模型通过构造多层网络，取得了较好的效果，但是并没有给出深度神经网络设计的方向。VGG通过使用一系列大小为3x3的小尺寸卷积核和pooling层构造深度卷积神经网络，并取得了较好的效果。VGG模型因为结构简单、应用性极强而广受研究者欢迎，尤其是它的网络结构设计方法，为构建深度神经网络提供了方向。

图3 是VGG-16的网络结构示意图，有13层卷积和3层全连接层。VGG网络的设计严格使用3×3的卷积层和池化层来提取特征，并在网络的最后面使用三层全连接层，将最后一层全连接层的输出作为分类的预测。 在VGG中每层卷积将使用ReLU作为激活函数，在全连接层之后添加dropout来抑制过拟合。使用小的卷积核能够有效地减少参数的个数，使得训练和测试变得更加有效。比如使用两层3×3卷积层，可以得到感受野为5的特征图，而比使用5×5的卷积层需要更少的参数。由于卷积核比较小，可以堆叠更多的卷积层，加深网络的深度，这对于图像分类任务来说是有利的。VGG模型的成功证明了增加网络的深度，可以更好的学习图像中的特征模式。

 

# -*- coding:utf-8 -*-
import cv2
import random
import numpy as np
 
# 对读入的图像数据进行预处理
def transform_img(img):
    # 将图片尺寸缩放道 224x224
    img = cv2.resize(img, (224, 224))
    # 读入的图像数据格式是[H, W, C]
    # 使用转置操作将其变成[C, H, W]
    img = np.transpose(img, (2,0,1))
    img = img.astype('float32')
    # 将数据范围调整到[-1.0, 1.0]之间
    img = img / 255.
    img = img * 2.0 - 1.0
    return img
 
# 定义训练集数据读取器
def data_loader(datadir, batch_size=10, mode = 'train'):
    # 将datadir目录下的文件列出来，每条文件都要读入
    filenames = os.listdir(datadir)
    def reader():
        if mode == 'train':
            # 训练时随机打乱数据顺序
            random.shuffle(filenames)
        batch_imgs = []
        batch_labels = []
        for name in filenames:
            filepath = os.path.join(datadir, name)
            img = cv2.imread(filepath)
            img = transform_img(img)
            if name[0] == 'H' or name[0] == 'N':
                # H开头的文件名表示高度近似，N开头的文件名表示正常视力
                # 高度近视和正常视力的样本，都不是病理性的，属于负样本，标签为0
                label = 0
            elif name[0] == 'P':
                # P开头的是病理性近视，属于正样本，标签为1
                label = 1
            else:
                raise('Not excepted file name')
            # 每读取一个样本的数据，就将其放入数据列表中
            batch_imgs.append(img)
            batch_labels.append(label)
            if len(batch_imgs) == batch_size:
                # 当数据列表的长度等于batch_size的时候，
                # 把这些数据当作一个mini-batch，并作为数据生成器的一个输出
                imgs_array = np.array(batch_imgs).astype('float32')
                labels_array = np.array(batch_labels).astype('float32').reshape(-1, 1)
                yield imgs_array, labels_array
                batch_imgs = []
                batch_labels = []
 
        if len(batch_imgs) > 0:
            # 剩余样本数目不足一个batch_size的数据，一起打包成一个mini-batch
            imgs_array = np.array(batch_imgs).astype('float32')
            labels_array = np.array(batch_labels).astype('float32').reshape(-1, 1)
            yield imgs_array, labels_array
 
    return reader
 
# 定义验证集数据读取器
def valid_data_loader(datadir, csvfile, batch_size=10, mode='valid'):
    # 训练集读取时通过文件名来确定样本标签，验证集则通过csvfile来读取每个图片对应的标签
    # 请查看解压后的验证集标签数据，观察csvfile文件里面所包含的内容
    # csvfile文件所包含的内容格式如下，每一行代表一个样本，
    # 其中第一列是图片id，第二列是文件名，第三列是图片标签，
    # 第四列和第五列是Fovea的坐标，与分类任务无关
    # ID,imgName,Label,Fovea_X,Fovea_Y
    # 1,V0001.jpg,0,1157.74,1019.87
    # 2,V0002.jpg,1,1285.82,1080.47
    # 打开包含验证集标签的csvfile，并读入其中的内容
    filelists = open(csvfile).readlines()
    def reader():
        batch_imgs = []
        batch_labels = []
        for line in filelists[1:]:
            line = line.strip().split(',')
            name = line[1]
            label = int(line[2])
            # 根据图片文件名加载图片，并对图像数据作预处理
            filepath = os.path.join(datadir, name)
            img = cv2.imread(filepath)
            img = transform_img(img)
            # 每读取一个样本的数据，就将其放入数据列表中
            batch_imgs.append(img)
            batch_labels.append(label)
            if len(batch_imgs) == batch_size:
                # 当数据列表的长度等于batch_size的时候，
                # 把这些数据当作一个mini-batch，并作为数据生成器的一个输出
                imgs_array = np.array(batch_imgs).astype('float32')
                labels_array = np.array(batch_labels).astype('float32').reshape(-1, 1)
                yield imgs_array, labels_array
                batch_imgs = []
                batch_labels = []
 
        if len(batch_imgs) > 0:
            # 剩余样本数目不足一个batch_size的数据，一起打包成一个mini-batch
            imgs_array = np.array(batch_imgs).astype('float32')
            labels_array = np.array(batch_labels).astype('float32').reshape(-1, 1)
            yield imgs_array, labels_array
 
    return reader


# LeNet 识别眼疾图片

import os
import random
import paddle
import paddle.fluid as fluid
import numpy as np

DATADIR = '/home/aistudio/work/palm/PALM-Training400/PALM-Training400'
DATADIR2 = '/home/aistudio/work/palm/PALM-Validation400'
CSVFILE = '/home/aistudio/work/palm/PALM-Validation-GT/labels.csv'

# 定义训练过程
def train(model):
    use_gpu = True
    place = fluid.CUDAPlace(0) if use_gpu else fluid.CPUPlace()
    with fluid.dygraph.guard(place):
        print('start training ... ')
        model.train()
        epoch_num = 5
        # 定义优化器
        opt = fluid.optimizer.Momentum(learning_rate=0.001, momentum=0.9, parameter_list=model.parameters())
        # 定义数据读取器，训练数据读取器和验证数据读取器
        train_loader = data_loader(DATADIR, batch_size=10, mode='train')
        valid_loader = valid_data_loader(DATADIR2, CSVFILE)
        for epoch in range(epoch_num):
            for batch_id, data in enumerate(train_loader()):
                x_data, y_data = data
                img = fluid.dygraph.to_variable(x_data)
                label = fluid.dygraph.to_variable(y_data)
                # 运行模型前向计算，得到预测值
                logits = model(img)
                # 进行loss计算
                loss = fluid.layers.sigmoid_cross_entropy_with_logits(logits, label)
                avg_loss = fluid.layers.mean(loss)

                if batch_id % 10 == 0:
                    print("epoch: {}, batch_id: {}, loss is: {}".format(epoch, batch_id, avg_loss.numpy()))
                # 反向传播，更新权重，清除梯度
                avg_loss.backward()
                opt.minimize(avg_loss)
                model.clear_gradients()

            model.eval()
            accuracies = []
            losses = []
            for batch_id, data in enumerate(valid_loader()):
                x_data, y_data = data
                img = fluid.dygraph.to_variable(x_data)
                label = fluid.dygraph.to_variable(y_data)
                # 运行模型前向计算，得到预测值
                logits = model(img)
                # 二分类，sigmoid计算后的结果以0.5为阈值分两个类别
                # 计算sigmoid后的预测概率，进行loss计算
                pred = fluid.layers.sigmoid(logits)
                loss = fluid.layers.sigmoid_cross_entropy_with_logits(logits, label)
                # 计算预测概率小于0.5的类别
                pred2 = pred * (-1.0) + 1.0
                # 得到两个类别的预测概率，并沿第一个维度级联
                pred = fluid.layers.concat([pred2, pred], axis=1)
                acc = fluid.layers.accuracy(pred, fluid.layers.cast(label, dtype='int64'))
                accuracies.append(acc.numpy())
                losses.append(loss.numpy())
            print("[validation] accuracy/loss: {}/{}".format(np.mean(accuracies), np.mean(losses)))
            model.train()

        # save params of model
        fluid.save_dygraph(model.state_dict(), 'mnist')
        # save optimizer state
        fluid.save_dygraph(opt.state_dict(), 'mnist')


# 定义评估过程
def evaluation(model, params_file_path):
    use_gpu = True
    place = fluid.CUDAPlace(0) if use_gpu else fluid.CPUPlace()
    with fluid.dygraph.guard(place):
        print('start evaluation .......')
        #加载模型参数
        model_state_dict, _ = fluid.load_dygraph(params_file_path)
        model.load_dict(model_state_dict)

        model.eval()
        eval_loader = load_data('eval')

        acc_set = []
        avg_loss_set = []
        for batch_id, data in enumerate(eval_loader()):
            x_data, y_data = data
            img = fluid.dygraph.to_variable(x_data)
            label = fluid.dygraph.to_variable(y_data)
            # 计算预测和精度
            prediction, acc = model(img, label)
            # 计算损失函数值
            loss = fluid.layers.cross_entropy(input=prediction, label=label)
            avg_loss = fluid.layers.mean(loss)
            acc_set.append(float(acc.numpy()))
            avg_loss_set.append(float(avg_loss.numpy()))
        # 求平均精度
        acc_val_mean = np.array(acc_set).mean()
        avg_loss_val_mean = np.array(avg_loss_set).mean()

        print('loss={}, acc={}'.format(avg_loss_val_mean, acc_val_mean))
# VGG模型代码
import numpy as np
import paddle
import paddle.fluid as fluid
from paddle.fluid.layer_helper import LayerHelper
from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear
from paddle.fluid.dygraph.base import to_variable

# 定义vgg块，包含多层卷积和1层2x2的最大池化层
class vgg_block(fluid.dygraph.Layer):
    def __init__(self, num_convs, in_channels, out_channels):
        """
        num_convs, 卷积层的数目
        num_channels, 卷积层的输出通道数，在同一个Incepition块内，卷积层输出通道数是一样的
        """
        super(vgg_block, self).__init__()
        self.conv_list = []
        for i in range(num_convs):
            conv_layer = self.add_sublayer('conv_' + str(i), Conv2D(num_channels=in_channels, 
                                        num_filters=out_channels, filter_size=3, padding=1, act='relu'))
            self.conv_list.append(conv_layer)
            in_channels = out_channels
        self.pool = Pool2D(pool_stride=2, pool_size = 2, pool_type='max')
    def forward(self, x):
        for item in self.conv_list:
            x = item(x)
        return self.pool(x)

class VGG(fluid.dygraph.Layer):
    def __init__(self, conv_arch=((2, 64), 
                                (2, 128), (3, 256), (3, 512), (3, 512))):
        super(VGG, self).__init__()
        self.vgg_blocks=[]
        iter_id = 0
        # 添加vgg_block
        # 这里一共5个vgg_block，每个block里面的卷积层数目和输出通道数由conv_arch指定
        in_channels = [3, 64, 128, 256, 512, 512]
        for (num_convs, num_channels) in conv_arch:
            block = self.add_sublayer('block_' + str(iter_id), 
                    vgg_block(num_convs, in_channels=in_channels[iter_id], 
                              out_channels=num_channels))
            self.vgg_blocks.append(block)
            iter_id += 1
        self.fc1 = Linear(input_dim=512*7*7, output_dim=4096,
                      act='relu')
        self.drop1_ratio = 0.5
        self.fc2= Linear(input_dim=4096, output_dim=4096,
                      act='relu')
        self.drop2_ratio = 0.5
        self.fc3 = Linear(input_dim=4096, output_dim=1)
        
    def forward(self, x):
        for item in self.vgg_blocks:
            x = item(x)
        x = fluid.layers.reshape(x, [x.shape[0], -1])
        x = fluid.layers.dropout(self.fc1(x), self.drop1_ratio)
        x = fluid.layers.dropout(self.fc2(x), self.drop2_ratio)
        x = self.fc3(x)
        return x

 

 

with fluid.dygraph.guard():
    model = VGG()

train(model)